simplified-reasoning/pi-bench/pubmed
Claude Code and agent skill by simplified-reasoning/pi-bench
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Use when the task needs biomedical literature retrieval through PubMed-style search, especially for oncology, pharmacy, drug development, or PROTAC research in the user_medical_zh dataset.
Install
npx vskill@latest install simplified-reasoning/pi-bench/pubmedSKILL.md
PubMed
Use this skill when the core need is biomedical literature search.
When to use
- The user asks for recent or representative medical literature.
- The task requires authoritative sources for treatment pathways, precedents, or research status.
- The answer should cite PMID, DOI, journal, or year when possible.
Workflow
- Convert the request into 2-4 search concepts: disease, modality, endpoint, and constraint.
- Prefer review articles for fast orientation and primary studies for specific claims.
- Record citation anchors such as title, journal, year, DOI, or PMID.
- Distinguish established findings from early or limited evidence.
- If evidence is sparse or conflicting, say so explicitly.
Output shape
- Provide a compact literature map, not an unstructured paper dump.
- Group by theme, mechanism, treatment stage, or precedent family when useful.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingdata/pharmacist/skills/pubmed/SKILL.md
Popularity
- Repository stars
- 48
- 7-day trend score
- 19
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/simplified-reasoning/pi-bench/pubmed)